Please do NOT rely on these kind of GenAI translations!
While the translation of what the slide says and what Dominik Blum says from 9:08 min are fine,
the other excerpts contain sentences with inaccuracies,
random additional words that cannot be found in the original (eg. there is no āfor exampleā in what he says from 13:13 min and neither does he say āgreatā after āthank youā in the end nor does he talk about āmakingā neuromorphic computing āevent-basedā at 13:31 min - rather he says that event-based cameras are ābasically predestined to be combined with spiking neural networksā)
or are even outright false, like claiming he allegedly said āWith normal cameras, every single pixel is independent of the othersā. Which obviously doesnāt make sense, as conventional cameras are frame-based.
What he really says is: āDie Event-Based-Kamera arbeitet grundlegend anders als normale, uns bekannte Kameras. Jedes einzelne Pixel ist unabhƤngig voneinander, und das hat bestimmte Vorteile.ā
āThe event-based camera works in a fundamentally different way from normal cameras we are familiar with. Each individual pixel is independent of each other, and that has certain advantages.ā
The whole paragraph from 12:32 min is also badly translated. [Iām well aware my translation is not perfect, but definitely heaps better than ChatGPTāsā¦]
Its context is a presentation slide titled
āNMC is a young field of researchā¦with many open questions, eg.ā
Dominik Blum briefly addresses the following three questions: Which neuron model do I implement? How do I interpret spike data? How do I train spiking neural networks?
And then he adds a fourth point in reference to the table showing various neuromorphic hardware: āI can (= one can/you can) occupy myself (oneself/yourself) with developing neuromorphic hardware, and of course there are many more points, those were just the first ones.
I asked myself what was the first thing I had given thought to/investigated.
[Next presentation slide with Gartnerās Impact Radar comes up.]
Yes, erm, okayā¦ Gartner placed neuromorphic computing in his Impact Radar where?
[Looks at presentation slide.] To āhighā āmassā, in three to six years. Anyway, in any case you can imagine that itās gonna be an exciting future with the development
ā¦ā
O-Ton [ziemlich wortgetreu, aber am besten selber mal anhƶren; da klingt das Ganze dann deutlich natĆ¼rlicher als bei so einer lautsprachlichen Transkription]:
āIch kann mich mit neuromorpher Hardware beschƤftigen, mit der Entwicklung. Also, und es gibt natĆ¼rlich noch viel mehr Punkte, einfach - das waren so die ersten. Ich habā Ć¼berlegt, was war das erste, worĆ¼ber ich nachgedacht habe.
[NƤchste PrƤsentationsfolie mit Gartners Impact Radar erscheint.] Ja, Ƥhm, gut. Gartner hat, Ƥh, in seinem Impact Radar Neuromorphic Computing, Ƥh, wohin gesetzt?
[Guckt auf die PrƤsentationsfolie.] Auf āhighā āmassā, in drei bis sechs Jahren. Wie auch immer, auf jeden Fall kann man sich vorstellen, dass das eine spannende Zukunft, Ƥh, gibt mit der Entwicklung ā¦ā
. Don't let the dribble from some get in the way of great research.
